Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement
cs.CV, cs.AI, cs.CL, cs.LG
Submitted: 2026-02-08
Updated: 2026-11-18
Project page: https://zhaoj9014.github.io
Terminology
Sources
- GPT-4 Technical Report
- Gemini: A Family of Highly Capable Multimodal Models
- Gemma: Open Models Based on Gemini Research and Technology
- DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
- DeepSeek-V3 Technical Report
- DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
- DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
- LLaMA: Open and Efficient Foundation Language Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Qwen2.5-VL Technical Report
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Training Compute-Optimal Large Language Models
- FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis
- LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
- Viziometrics: Analyzing Visual Information in the Scientific Literature
- FigureNet: A Deep Learning model for Question-Answering on Scientific Plots
- Look, Read and Enrich. Learning from Scientific Figures and their Captions
- RealCQA: Scientific Chart Question Answering as a Test-bed for First-Order Logic
- ACL-Fig: A Dataset for Scientific Figure Classification
- Every Part Matters: Integrity Verification of Scientific Figures Based on Multimodal Large Language Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs